INDEX

Explanations

terms related to specific brain regions, particularly the prefrontal cortex and parietal lobe

oai_token-act-pair · gpt-3.5-turbo

references to neurological structures and their functions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rave

-0.84

Rated

-0.83

soDeliveryDate

-0.78

 Breed

-0.75

lust

-0.74

STON

-0.73

 Slayer

-0.72

Deal

-0.71

Cash

-0.69

INGTON

-0.68

POSITIVE LOGITS

 lobe

1.44

 cortex

1.26

 cortical

1.15

lob

1.11

 anterior

0.99

 prefrontal

0.99

rontal

0.94

 dopamine

0.93

 hippocampus

0.93

 neurons

0.89

Activations Density 0.095%

terms related to specific brain regions, particularly the prefrontal cortex and parietal lobe

references to neurological structures and their functions

No Comments

No Known Activations